This page lists three turns, the messages you send to the AI one after another in the same chat, and then a check of the answer. Keep it open next to your chat. Each turn shows the next thing to paste, with the values you entered already filled in. Nothing is sent from this page, and your conversation stays in the AI tool you are using.
Your one-line theme plus the two or three pillars that must be proved.
Each witness with role, what they prove, exhibits they authenticate, and expected direct length.
Days allotted to your case and the actual trial-day hours.
Forum and judge, including any time limits or standing-order rules that constrain the sequence.
Sequencing changes completely depending on whether you are opening the evidence or answering it.
Availability windows, travel, experts on the clock, subpoena limits, health issues.
Watch for these throughout
Trial slippage is the rule, not the exception. If the sequence only works without the 25% buffer, it does not work.
Witness availability overrides strategy every time. Confirm every out-of-town witness and expert before committing to a slot.
Judges vary enormously on time limits, chess-clock rules, and whether they will let you call a witness out of order. Check the standing order, not the model's assumption.
The model will treat every exhibit as admissible. If an in-limine ruling goes against you, the witness carrying that exhibit may lose their reason to be in the slot.
Calling an adverse decisionmaker in your case in chief is a genuine two-sided bet. The model tends to favor it; the downside is a full dress rehearsal for the other side.